Show simple item record

dc.contributor.author
Opfer, Roland
dc.contributor.author
Krueger, Julia
dc.contributor.author
Spies, Lothar
dc.contributor.author
Ostwaldt, Ann-Christin
dc.contributor.author
Kitzler, Hagen H.
dc.contributor.author
Schippling, Sven
dc.contributor.author
Buchert, Ralph
dc.date.accessioned
2023-03-28T08:39:30Z
dc.date.available
2022-10-29T05:34:37Z
dc.date.available
2022-10-31T07:47:31Z
dc.date.available
2023-02-14T08:03:57Z
dc.date.available
2023-03-28T08:39:30Z
dc.date.issued
2023-03
dc.identifier.issn
0938-7994
dc.identifier.issn
1432-1084
dc.identifier.other
10.1007/s00330-022-09170-y
en_US
dc.identifier.uri
http://hdl.handle.net/20.500.11850/578385
dc.identifier.doi
10.3929/ethz-b-000578385
dc.description.abstract
Objectives To develop an automatic method for accurate and robust thalamus segmentation in T1w-MRI for widespread clinical use without the need for strict harmonization of acquisition protocols and/or scanner-specific normal databases. Methods A three-dimensional convolutional neural network (3D-CNN) was trained on 1975 T1w volumes from 170 MRI scanners using thalamus masks generated with FSL-FIRST as ground truth. Accuracy was evaluated with 18 manually labeled expert masks. Intra- and inter-scanner test-retest stability were assessed with 477 T1w volumes of a single healthy subject scanned on 123 MRI scanners. The sensitivity of 3D-CNN-based volume estimates for the detection of thalamus atrophy was tested with 127 multiple sclerosis (MS) patients and a normal database comprising 4872 T1w volumes from 160 scanners. The 3D-CNN was compared with a publicly available 2D-CNN (FastSurfer) and FSL. Results The Dice similarity coefficient of the automatic thalamus segmentation with manual expert delineation was similar for all tested methods (3D-CNN and FastSurfer 0.86 +/- 0.02, FSL 0.87 +/- 0.02). The standard deviation of the single healthy subject's thalamus volume estimates was lowest with 3D-CNN for repeat scans on the same MRI scanner (0.08 mL, FastSurfer 0.09 mL, FSL 0.15 mL) and for repeat scans on different scanners (0.28 mL, FastSurfer 0.62 mL, FSL 0.63 mL). The proportion of MS patients with significantly reduced thalamus volume was highest for 3D-CNN (24%, FastSurfer 16%, FSL 11%). Conclusion The novel 3D-CNN allows accurate thalamus segmentation, similar to state-of-the-art methods, with considerably improved robustness with respect to scanner-related variability of image characteristics. This might result in higher sensitivity for the detection of disease-related thalamus atrophy.
en_US
dc.format
application/pdf
en_US
dc.language.iso
en
en_US
dc.publisher
Springer
en_US
dc.rights.uri
http://creativecommons.org/licenses/by/4.0/
dc.subject
Thalamus
en_US
dc.subject
Magnetic resonance imaging
en_US
dc.subject
Neural networks
en_US
dc.subject
Multiple sclerosis
en_US
dc.title
Automatic segmentation of the thalamus using a massively trained 3D convolutional neural network: higher sensitivity for the detection of reduced thalamus volume by improved inter-scanner stability
en_US
dc.type
Journal Article
dc.rights.license
Creative Commons Attribution 4.0 International
dc.date.published
2022-10-20
ethz.journal.title
European Radiology
ethz.journal.volume
33
en_US
ethz.journal.issue
3
en_US
ethz.journal.abbreviated
Eur Radiol
ethz.pages.start
1852
en_US
ethz.pages.end
1861
en_US
ethz.version.deposit
publishedVersion
en_US
ethz.identifier.wos
ethz.identifier.scopus
ethz.publication.place
New York, NY
en_US
ethz.publication.status
published
en_US
ethz.date.deposited
2022-10-29T05:34:40Z
ethz.source
WOS
ethz.eth
yes
en_US
ethz.availability
Open access
en_US
ethz.rosetta.installDate
2023-03-28T08:39:31Z
ethz.rosetta.lastUpdated
2024-02-02T21:21:11Z
ethz.rosetta.versionExported
true
ethz.COinS
ctx_ver=Z39.88-2004&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.atitle=Automatic%20segmentation%20of%20the%20thalamus%20using%20a%20massively%20trained%203D%20convolutional%20neural%20network:%20higher%20sensitivity%20for%20the%20detection%&rft.jtitle=European%20Radiology&rft.date=2023-03&rft.volume=33&rft.issue=3&rft.spage=1852&rft.epage=1861&rft.issn=0938-7994&1432-1084&rft.au=Opfer,%20Roland&Krueger,%20Julia&Spies,%20Lothar&Ostwaldt,%20Ann-Christin&Kitzler,%20Hagen%20H.&rft.genre=article&rft_id=info:doi/10.1007/s00330-022-09170-y&
 Search print copy at ETH Library

Files in this item

Thumbnail

Publication type

Show simple item record